BEGIN:VCALENDAR VERSION:2.0 PRODID:Linklings LLC BEGIN:VTIMEZONE TZID:Asia/Seoul X-LIC-LOCATION:Asia/Seoul BEGIN:STANDARD TZOFFSETFROM:+0900 TZOFFSETTO:+0900 TZNAME:KST DTSTART:18871231T000000 DTSTART:19881009T020000 END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20230103T035307Z LOCATION:Auditorium\, Level 5\, West Wing DTSTART;TZID=Asia/Seoul:20221206T100000 DTEND;TZID=Asia/Seoul:20221206T120000 UID:siggraphasia_SIGGRAPH Asia 2022_sess153_papers_171@linklings.com SUMMARY:Learning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptation DESCRIPTION:Technical Papers\n\nLearning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptation\n\nYeh, Nagano, Khami s, Kautz, Liu...\n\nGiven a portrait image of a person and an environment map of the target lighting, portrait relighting aims to re-illuminate the person in the image as if the person appeared in an environment with the t arget lighting. To achieve high-quality results, recent methods rely on de ep learning. An effective approach is to supervise the training of deep ne ural networks with a high-fidelity dataset of desired input--output pairs, captured with a light stage. However, acquiring such data requires an exp ensive special capture rig and time-consuming efforts, limiting access to only a few resourceful laboratories. To address the limitation, we propose a new approach that can perform on par with the state-of-the-art (SOTA) r elighting methods without requiring a light stage. Our approach is based o n the realization that a successful relighting of a portrait image depends on two conditions. First, the physics of light transport has to be correc t. Second, the output has to be photorealistic. To meet the first conditio n, we propose to train the relighting network with training data generated by a virtual light stage that performs physically-based rendering on vari ous 3D synthetic humans under different environment maps. To meet the seco nd condition, we develop a novel synthetic-to-real approach to bring photo realism to the relighting network output. In addition to achieving SOTA re sults, our approach offers several advantages over the prior methods, incl uding controllable glares on glasses and more temporally-consistent result s for relighting videos.\n\nRegistration Category: FULL ACCESS, EXPERIENCE PLUS ACCESS, EXPERIENCE ACCESS, TRADE EXHIBITOR\n\nLanguage: ENGLISH\n\nF ormat: IN-PERSON URL:https://sa2022.siggraph.org/en/full-program/?id=papers_171&sess=sess15 3 END:VEVENT END:VCALENDAR